A system for learning statistical motion patterns

By Weiming Hu, Xuejuan Xiao, Zhouyu Fu, Dan Xie, Tien-Ping Tan, S. Maybank. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006

608 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Signal Processing

View Paper: https://www.semanticscholar.org/paper/f1f19b19a1293a7b728b4c445385199e797bcb97

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Signal Processing

Citations in the corpus

Trajectory Learning for Activity Understanding: Unsupervised, Multilevel, and Long-Term Adaptive Approach (2011, methodology): “The HMM-based formulation does not impose global temporal alignment, unlike other probabilistic spatiotemporal activity representations [15].”
Online detection of unusual events in videos via dynamic sparse coding (2011, background): “Specifically, [7, 20, 9] studies the problem using tracking trajectories.”
A survey on motion prediction and risk assessment for intelligent vehicles (2014, unknown): “The simplest solution to predict future motion after the distance to each motion pattern has been computed is to select the most likely motion pattern and to use it as a unique model [[36]].”
Anomaly detection in extremely crowded scenes using spatio-temporal motion pattern models (2009, background): “Deviation approaches model usual activity, detecting unusual events as those that differ from the pre-trained model [1, 3, 5, 8, 9, 13, 21, 23, 24, 25].”
Observe locally, infer globally: A space-time MRF for detecting abnormal activities with incremental updates (2009, background): “Tracking-based algorithms [2, 14, 9] determine the abnormality for each object’s trajectory.”
Sparse reconstruction cost for abnormal event detection (2011, background): “There are also some trajectory-based approaches to locate objects by tracking or frame-difference, such as [10], [24], [21] and [13].”
Video anomaly detection based on local statistical aggregates (2012, background): “This insight helps collapse the large ambient data dimension for detecting local anomalies.”
Outlier Detection (2008, background): “In this sense, depth functions can measure the “extremeness” or “outlyingness” of a data point with respect to a given data set.”
Robust Real-Time Unusual Event Detection using Multiple Fixed-Location Monitors (2008, methodology): “Nonparametric representations of actions were used in [34], using the histograms of spatio-temporal gradients.”
Trajectory-Based Anomalous Event Detection (2008, methodology): “[24] use a hierarchic clustering of trajectories depending on spatial and temporal information; Lou et al.”
Model-Based Probabilistic Collision Detection in Autonomous Driving (2009, background): “As reported in the literature, human driver prediction within the ego vehicle (i.e., the vehicle for which the safety assessment is performed) can be conducted with the help of learning mechanisms such as neural networks or filter techniques, as, e.g., Kalman filters.”
Vessel Pattern Knowledge Discovery from AIS Data: A Framework for Anomaly Detection and Route Prediction (2013, background): “Reference [12] presented an extensive model to statistically learn motion patterns without any prior knowledge in traffic scenes where the traffic flows are constrained to stay in specific areas.”
A Survey of Vision-Based Trajectory Learning and Analysis for Surveillance (2008, methodology): “Two simple techniques for length normalization are zero padding [36] and track extension [13], [49].”
Crowded Scene Analysis: A Survey (2015, background): “Video analysis and scene understanding usually involve object detection, tracking and behavior recognition [5], [6].”
Learning object motion patterns for anomaly detection and improved object detection (2008, background): “Hu et al. [7] present a recently published technique in which the tracks are spatially and temporally clustered into different motion patterns.”
STREETS: A Novel Camera Network Dataset for Traffic Flow (2019, background): “There are many other traffic camera datasets that utilize fewer than ten cameras and limit analysis to one intersection at a time [13, 14, 15, 16, 17, 18, 19, 20].”